import pandas as pd
import seaborn as sns
import plotly.express as px

import matplotlib.pyplot as plt

from plotly.offline import init_notebook_mode
init_notebook_mode(connected=True)

import plotly.io as pio
pio.renderers.default = "plotly_mimetype+notebook"

Matplotlib

For this excercise, we have written the following code to load the stock dataset built into plotly express.

stocks = px.data.stocks()
stocks.head()

	date	GOOG	AAPL	AMZN	FB	NFLX	MSFT
0	2018-01-01	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	2018-01-08	1.018172	1.011943	1.061881	0.959968	1.053526	1.015988
2	2018-01-15	1.032008	1.019771	1.053240	0.970243	1.049860	1.020524
3	2018-01-22	1.066783	0.980057	1.140676	1.016858	1.307681	1.066561
4	2018-01-29	1.008773	0.917143	1.163374	1.018357	1.273537	1.040708

Question 1:

Select a stock and create a suitable plot for it. Make sure the plot is readable with relevant information, such as date, values.

new_stocks = stocks.set_index("date")

plt.figure(figsize=(12,8))
new_stocks["GOOG"].plot()
plt.title("Google stock")
plt.xlabel("date")
plt.ylabel("stock value")

plt.show()

Question 2:

You've already plot data from one stock. It is possible to plot multiples of them to support comparison.
To highlight different lines, customise line styles, markers, colors and include a legend to the plot.

plt.figure(figsize=(12,8))
for c in new_stocks.columns:
    new_stocks[c].plot(label=c)
plt.title("Stock")
plt.xlabel("date")
plt.ylabel("stock value")
plt.legend()

plt.show()

Seaborn

First, load the tips dataset

tips = sns.load_dataset('tips')
tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

Question 3:

Let's explore this dataset. Pose a question and create a plot that support drawing answers for your question.

Some possible questions:

• Are there differences between male and female when it comes to giving tips?
• What attribute correlate the most with tip?

# YOUR CODE HERE
plt.figure(figsize=(10,3))
plt.subplot(1,2,1)
sns.scatterplot(x='tip', y='total_bill', data=tips[tips["sex"]=='Male'])
plt.xlim(0,11)
plt.ylim(0,55)
plt.title('male')

plt.subplot(1,2,2)
sns.scatterplot(x='tip', y='total_bill', data=tips[tips["sex"]=='Female'])
plt.xlim(0,11)
plt.ylim(0,55)
plt.title('female')
plt.show()

# OR:
sns.boxplot(x='sex', y='tip', data=tips)
plt.show()

Putting the outliers aside, it seems that women tend to tip a bit less, but all in all the same as men.

sns.heatmap(tips.corr(), cmap='YlGn', annot=True)
plt.show()

Based on the graph above we can conclude that total_bill correlates the most with tip. Because the correlation is 0.68.

Plotly Express

Question 4:

Redo the above exercises (challenges 2 & 3) with plotly express. Create diagrams which you can interact with.

The stocks dataset

Hints:

• Turn stocks dataframe into a structure that can be picked up easily with plotly express

modified_stocks = pd.melt(stocks, id_vars=['date'], var_name='name', value_name='value')
modified_stocks.head()

	date	name	value
0	2018-01-01	GOOG	1.000000
1	2018-01-08	GOOG	1.018172
2	2018-01-15	GOOG	1.032008
3	2018-01-22	GOOG	1.066783
4	2018-01-29	GOOG	1.008773

fig = px.line(modified_stocks, x='date', y='value', color='name', symbol='name')
fig.show()

The tips dataset

fig = px.scatter(tips, x='total_bill', y='tip', color='sex', facet_col='smoker', facet_row='time')
fig.show()

Question 5:

Recreate the barplot below that shows the population of different continents for the year 2007.

Hints:

• Extract the 2007 year data from the dataframe. You have to process the data accordingly
• use plotly bar
• Add different colors for different continents
• Sort the order of the continent for the visualisation. Use axis layout setting
• Add text to each bar that represents the population

#load data
df = px.data.gapminder()
df.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

pop = df.query("year == 2007")
pop_new = pop.groupby('continent').sum()
fig = px.bar(pop_new, x='pop', y=pop_new.index, color=pop_new.index, text_auto='.2s')
fig.update_yaxes(categoryorder = "total ascending")
fig.update_traces(textposition='outside')
fig.update_layout(showlegend=False)
fig.show()